# Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires

arXiv: https://arxiv.org/abs/2510.25384 · HTML: https://mlsanity.com/paper/2510.25384/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 29 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach](https://mlsanity.com/paper/2101.07714/) (2021)
- [Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory](https://mlsanity.com/paper/2407.03103/) (2024)
- [Enhancing Psychological Counseling with Large Language Model: A Multifaceted Decision-Support System for Non-Professionals](https://mlsanity.com/paper/2308.15192/) (2023)
- [Do Large Language Models Align with Core Mental Health Counseling Competencies?](https://mlsanity.com/paper/2410.22446/) (2024)
- [Collaborative Synthesis of Patient Records through Multi-Visit Health State Inference](https://mlsanity.com/paper/2312.14646/) (2023)
- [Towards Algorithmic Fidelity: Mental Health Representation across Demographics in Synthetic vs. Human-generated Data](https://mlsanity.com/paper/2403.16909/) (2024)

## Built on by (most cited first, 4 of 4)

- [PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics](https://mlsanity.com/paper/2601.03578/) (2026)
- [Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs](https://mlsanity.com/paper/2604.20382/) (2026)
- [Expert-Level Crisis Detection in Mental Health Conversations](https://mlsanity.com/paper/2606.10380/) (2026)
- [ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance](https://mlsanity.com/paper/2608.04524/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are promising tools for synthetic data generation in mental health. However, privacy policies and restrictions forced previous work to rely mainly on generic information. We present a comprehensive corpus of synthetic therapist-client conversations generated through LLMs. We construct our generation pipeline, SQPsych (Structured Questionnaire-based Psychotherapy), which uses real structured client profiles and psychological questionnaires without leaking any sensitive data. We fine-tune various open-weight LLMs on our generated corpus, SQPsychConv , and test them through both automatic benchmarks and human evaluation with trained psychotherapists. We find that standard benchmarks do not adequately capture the strengths of our dataset, but expert judgment shows that SQPsych makes LLMs significantly better at therapist roleplaying. Experts also consistently prefer therapy sessions generated by our models compared to other mental-health-oriented LLMs. We release our code, fine-tuned models SQPsychLLM, and corpora at https://ai-mh.github.io/SQPsych.html.